← Back to community benchmarks

Qwen2.5-Coder-7B-Instruct

M4 Pro (16c) · 24 GB · 4bit · 2026-03-21
Performance
16k
tokens
337.9
PP tok/s
38.3
TG tok/s
48491
TTFT (ms)
5.5
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.2.19
macOS macOS 26.2
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 403.7 54.9 4.8 GB view
4k 395.7 50.1 4.9 GB view
8k 376.5 44.2 5.0 GB view
16k 337.9 38.3 5.5 GB current
Batching Results
Batch Size TG tok/s Speedup
54.9 1.00×
86.6 1.58×
92.1 1.68×